Adaptive neural network based backstepping control design for MIMO nonlinear systems with actuator nonlinearities

作者：Jamil Muhammad Usman^*; Kongprawechnon Waree; Raza Muhammad Qamar

来源：Aircraft Engineering and Aerospace Technology, 2016, 88(1): 137-150.

DOI：10.1108/AEAT-09-2014-0150

• Backstepping
• Electrically driven robot manipulator (EDRM)
• Linear in parameter (LIP)
• Robust adaptive neural network (RANN)

Purpose - The purpose of the proposed research methodology is to control the trajectory tracking of EDRM and also to cancel out the effect of no-smooth nonlinearities, which affect the system performance badly.
Design/methodology/approach - Robust adaptive neural network (RANN)-based backstepping control design methodology is presented in this paper. The proposed design methodology improves the trajectory tracking and running mean error.
Findings - The running mean error results show that the convergence of the proposed RANN-based backstepping technique is very fast as compare to the conventional PD control and due to this proposed control technique, the EDRM follows its desired trajectory perfectly.
Practical implications - The EDRM trajectory tracking performance increases which leads to a better working position of EDRM.
Originality/value - The originality of this research article is 93 per cent.

• 出版日期2016